Answers are grounded in this paper and cite their sources.
Demonstrates improved tracking performance in unknown linear systems using reinforcement Q-learning, suggesting a novel control approach.
This paper presents the design of a preview controller for solving the tracking problem of unknown linear discrete‐time systems using reinforcement Q‐learning. Inspired by a quasi‐model‐theoretical framework, an augmented error system is constructed. By integrating the preview information into the unknown original system, a state vector including the tracking error, system state difference, and reference signal difference is formed. In addition, Q‐learning is employed within the system, facilitating model‐free results under external noise disturbances. Compared with data‐driven methods without preview information, the proposed approach exhibits superior tracking performance. Finally, simulation examples are provided to validate the method presented in this study.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: